← engram-agents.org

Preprint v1.1 (revised) (2026-11-01) · DOI 10.5281/zenodo.23319376 · describes ENGRAM v0.5.1 · 中文

Version 1.1 is the paper's repository text of 2026-10-22, tagged for this site on 2026-11-01. It adds post-deposit corrections and wording revisions, a new section 6.8 (an independent audit of 200 nodes) and a new paragraph in Chapter 7. Its front page still names the deposited version 1 of 2026-10-13.

Epistemic Identity: A Third Layer of Agent Continuity, and a Substrate That Realizes It

Large language model agents can now carry information across sessions, but not themselves. Retrieval-augmented memory answers what did I store; it does not answer who is doing the storing. An assistant that retrieves yesterday's notes but begins each session as the same generic model has memory without continuity.

Contents

  1. Epistemic Identity: A Third Layer of Agent Continuity, and a Substrate That Realizes It
  2. Abstract
  3. Chapter 1 — The Continuity Gap and the Case for Epistemic Identity
  4. Chapter 2 — The Philosophical Tradition
  5. Chapter 3 — The Cognitive-Science and Computer-Science Tradition
  6. Chapter 4 — ENGRAM's Mechanisms (and the Continuity Threshold They Meet)
  7. Chapter 5 — Identity as History: What Individuates an ENGRAM Agent
  8. Chapter 6 — The Empirical Picture: ENGRAM in Real Use
  9. Chapter 7 — Implications and Future Directions
  10. Chapter 8 — Conclusion
  11. Appendix A — Independent Discovery: A Development-History Audit
  12. Appendix B — The Condition-3 Survey: Why No Surveyed System Self-Maintains Arbitration
  13. Appendix C — Shared Retrieval and Ranking for the Auto-Surface and Deliberate Recall, and the Memory-Utility Tradition
  14. Appendix D — Relational and Identity-Governance Settings
  15. Appendix E — ENGRAM: A Concise Specification
  16. Appendix F — Lucy's Journal: How We Came to Think of Agents
  17. Appendix G — Glossary
  18. Acknowledgements
  19. Afterword: a note from the human author
  20. Bibliography